AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models
Authors:
- Alexandra ChronopoulouACAlexandra Chronopoulou
- Jesse DodgeJDJesse Dodge
Top Cited Papers
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 2054-2063
Abstract
Alexandra Chronopoulou, Matthew Peters, Alexander Fraser, Jesse Dodge. Findings of the Association for Computational Linguistics: EACL 2023. 2023.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- DEMix Layers: Disentangling Domains for Modular Language Modeling2022
- Efficient Hierarchical Domain Adaptation for Pretrained Language Models2022
- Efficient Test Time Adapter Ensembling for Low-resource Language Varieties2021
- Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus2021
- Transformers: State-of-the-Art Natural Language Processing2020
- MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer2020
- Unsupervised Domain Clusters in Pretrained Language Models2020
- Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks2020
- BioBERT: a pre-trained biomedical language representation model for biomedical text miningBioinformatics, 2019
- FaceNet: A unified embedding for face recognition and clustering2015